Výsledky vyhľadávania - dynamical system autoencoder~

Context-Dependent Manifold Learning in Dynamical Systems: A Neuromodulated Constrained Autoencoder Approach

Autori: Adriaens, Jérôme Drion, Guillaume Sacré, Pierre

Zdroj: Symmetry and Geometry in Neural Representations workshop, NeurIPS 2025, San Diego, United States - California [US-CA], Tuesday Dec 2nd through Sunday Dec 7th

Predmety: Nonlinear dimensionality reduction, Neuromodulation, Context-dependent learning, Constrained autoencoder, Engineering, computing & technology, Ingénierie, informatique & technologie

Prístupová URL adresa: https://orbi.uliege.be/handle/2268/336469

Sensor-Driven Surrogate Modeling and Control of Nonlinear Dynamical Systems Using FAE-CAE-LSTM and Deep Reinforcement Learning

Autori: Kherad, M. Moayyedi, M. K. Fotouhi-Ghazvini, F. a ďalší

Zdroj: Sensors. 25(16)

Predmety: Autoencoders, Control Of Dynamical Systems, Cyber-physical Systems, Deep Reinforcement Learning, Long Short-term Memory, Sensor-driven Modeling, Circular Cylinders, Computer Control Systems, Convolution, Dynamical Systems, Dynamics, Embedded Systems, Flow Control, Fuel Additives, Nonlinear Dynamical Systems, Real Time Control, Robust Control, Auto Encoders, Control Of Dynamical System, Cybe-physical Systems, High-dimensional, Higher-dimensional, Reinforcement Learning Agent, Reinforcement Learnings, Short Term Memory

Popis súboru: print

Prístupová URL adresa: https://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-73172
https://doi.org/10.3390/s25165149

Understanding the role of autoencoders for stiff dynamical systems using information theory

Autori: Vijayamanikandan Vijayarangan Harshavardhana A. Uranakara Francisco E. Hernández–Pérez a ďalší

Zdroj: Energy and AI, Vol 21, Iss , Pp 100567- (2025)

Predmety: Neural ODE, Autoencoders, Information bottleneck theory, Dynamical systems, Disentanglement, Electrical engineering. Electronics. Nuclear engineering, TK1-9971, Computer software, QA76.75-76.765

Popis súboru: electronic resource

Relation: http://www.sciencedirect.com/science/article/pii/S2666546825000990; https://doaj.org/toc/2666-5468

Prístupová URL adresa: https://doaj.org/article/0078f652db91496fbf58605196636ba7

Dynamical System Autoencoders

Autori: Shiquan He Randy Paffenroth Olivia Cava a ďalší

Zdroj: 2024 International Conference on Machine Learning and Applications (ICMLA). :1496-1503

Slim multi-scale convolutional autoencoder-based reduced-order models for interpretable features of a complex dynamical system

Autori: Teutsch, Philipp Pfeffer, Philipp Ghazijahani, Mohammad Sharifi a ďalší

Témy: Physics - Fluid Dynamics, Computer Science - Machine Learning, text

URL: http://arxiv.org/abs/2501.03070

Slim multi-scale convolutional autoencoder-based reduced-order models for interpretable features of a complex dynamical system

Autori: Philipp Teutsch Philipp Pfeffer Mohammad Sharifi Ghazijahani a ďalší

Zdroj: APL Machine Learning, Vol 3, Iss 1, Pp 016112-016112-15 (2025)

Predmety: FOS: Computer and information sciences, Computer Science - Machine Learning, Physics, QC1-999, Electronic computers. Computer science, Fluid Dynamics (physics.flu-dyn), FOS: Physical sciences, QA75.5-76.95, Physics - Fluid Dynamics, Machine Learning (cs.LG)

Prístupová URL adresa: http://arxiv.org/abs/2501.03070
https://doaj.org/article/236f8e1f2be64001a1d9c1d7b38ae1f2

MODELING UNKNOWN STOCHASTIC DYNAMICAL SYSTEM VIA AUTOENCODER

Autori: Xu, Zhongshu Chen, Yuan Chen, Qifan a ďalší

Zdroj: Journal of Machine Learning for Modeling and Computing. 5:87-112

Predmety: FOS: Computer and information sciences, Computer Science - Machine Learning, Statistics - Machine Learning, FOS: Mathematics, Machine Learning (stat.ML), Mathematics - Numerical Analysis, Numerical Analysis (math.NA), 60H10, 60H35, 62M45, 65C30, Machine Learning (cs.LG)

Prístupová URL adresa: http://arxiv.org/abs/2312.10001

Dynamical system autoencoders using piecewise linear transformation

Autori: Shiquan He Randy Paffenroth

Zdroj: Seventh International Conference on Image, Video Processing, and Artificial Intelligence (IVPAI 2025). :24

Lipschitz Stabilised Autoencoders to Study the Intrinsic Dimensionality of Dynamical Systems and Build Data-driven Models

Autori: Liu, Haibo Lombardi, Damiano Boulakia, Muriel

Prispievatelia: Liu, Haibo Lombardi, Damiano Boulakia, Muriel

Predmety: [MATH] Mathematics [math]

Prístupová URL adresa: https://hal.science/hal-04398549v1

Lipschitz Stabilised Autoencoders in Parameter Identification of Dynamical Systems

Autori: Liu, Haibo Lombardi, Damiano Boulakia, Muriel

Prispievatelia: Liu, Haibo Lombardi, Damiano Boulakia, Muriel

Predmety: [MATH] Mathematics [math]

Prístupová URL adresa: https://hal.science/hal-04398536v1

Echo state network and variational autoencoder for efficient one-class learning on dynamical systems

Autori: Cabrera, Diego Sancho, Fernando Cerrada, Mariela a ďalší

Zdroj: Journal of Intelligent & Fuzzy Systems. 34:3799-3809

Predmety: 0202 electrical engineering, electronic engineering, information engineering, Deep learning, 02 engineering and technology, 0101 mathematics, Dynamical system modeling, Variational inference, 01 natural sciences, Reservoir computing

Popis súboru: application/pdf

Prístupová URL adresa: https://content.iospress.com/articles/journal-of-intelligent-and-fuzzy-systems/ifs169552
http://repositorio.uchile.cl/handle/2250/152469
https://dblp.uni-trier.de/db/journals/jifs/jifs34.html#CabreraSCST18

Modeling Unknown Stochastic Dynamical System via Autoencoder

Autori: Xu, Zhongshu Chen, Yuan Chen, Qifan a ďalší

Témy: Computer Science - Machine Learning, Mathematics - Numerical Analysis, Statistics - Machine Learning, 60H10, 60H35, 62M45, 65C30, text

URL: http://arxiv.org/abs/2312.10001

Autoencoders as Dynamical Systems

Autori: Theses, Monash University Cook, Andrew James Heinze

Predmety: Dynamical systems in applications, Neural networks

A density-based manifold learning framework for reconstructing high-dimensional dynamical systems with outliers.

Autori: Xue, Qing Du, Lin Jiang, Feng a ďalší

Zdroj: Physica D. Dec2025, Vol. 483, pN.PAG-N.PAG. 1p.

Predmety: *DYNAMICAL systems, *OUTLIERS (Statistics), *CLUSTERING algorithms, *CLUSTER analysis (Statistics), *AUTOENCODERS, *DIMENSIONAL reduction algorithms

Topological properties of basins of attraction of width bounded autoencoders.

Autori: Beise, Hans-Peter Da Cruz, Steve Dias

Zdroj: Analysis & Applications. Aug2024, Vol. 22 Issue 6, p965-980. 16p.

Predmety: *TOPOLOGICAL property, *DYNAMICAL systems

Generative Adversarial Network based Autoencoder: Application to fault detection problem for closed loop dynamical systems

Autori: Chakraborty, Indrasis Chakraborty, Rudrasis Vrabie, Draguna

Témy: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning, text

URL: http://arxiv.org/abs/1804.05320

Adaptive Path-Integral Autoencoder: Representation Learning and Planning for Dynamical Systems

Autori: Ha, Jung-Su Park, Young-Jin Chae, Hyeok-Joo a ďalší

Témy: Computer Science - Machine Learning, Computer Science - Robotics, Statistics - Machine Learning, text

URL: http://arxiv.org/abs/1807.02128

Dynamical system reconstruction from partial observations using stochastic dynamics

Autori: Sip, Viktor Breyton, Martin Petkoski, Spase a ďalší

Predmety: Machine Learning, FOS: Computer and information sciences, FOS: Biological sciences, Quantitative Methods, Quantitative Methods (q-bio.QM), Machine Learning (cs.LG)

Prístupová URL adresa: http://arxiv.org/abs/2510.01089

Autoencoding for the 'Good Dictionary' of eigenpairs of the Koopman operator

Autori: Neranjaka Jayarathne Erik M. Bollt

Zdroj: AIMS Mathematics, Vol 9, Iss 1, Pp 998-1022 (2024)

Predmety: FOS: Computer and information sciences, reduced order modelling, deep learning, data driven science, Computer Science - Neural and Evolutionary Computing, Dynamical Systems (math.DS), 37B05, autoencoders, koopman analysis, QA1-939, FOS: Mathematics, Neural and Evolutionary Computing (cs.NE), Mathematics - Dynamical Systems, Mathematics

Prístupová URL adresa: http://arxiv.org/abs/2306.05224
https://doaj.org/article/bebaebe20ace4bf6877d9adf089505c4

Flow control by a hybrid use of machine learning and control theory.

Autori: Ishize, Takeru Omichi, Hiroshi Fukagata, Koji

Zdroj: International Journal of Numerical Methods for Heat & Fluid Flow. 2024, Vol. 34 Issue 8, p3253-3277. 25p.

Predmety: *FLOW velocity, *LINEAR dynamical systems, *FLUID control, *LINEAR control systems, *FLUID flow